The dragonfly topology has been proposed as an efficient alternative to the fat tree. This talk presents a study of the blocking and scalability characteristics of the dragonfly, and compares this to the well-known fat tree topology.
Search Results for: comparison
Joe Landman and the fine folks at Scalable Informatics have just published a new whitepaper [PDF] comparing the performance of the National Center for Biotechnology Information’s BLAST application on Magny Cours, Istanbul, and Nehalem. According to the Wikipedia In bioinformatics, Basic Local Alignment Search Tool, or BLAST, is an algorithm for comparing primary biological sequence […]
I’ve had several requests for links to benchmark data on the new AMD and Intel processors that have launched over the past couple weeks. We added a little bit of information with our posting of SGI’s SPEC results for its forthcoming UV line running the Xeon 7500s. Yesterday one of AMD’s marketing drones pointed to […]
Melissa Norr at the CRA Policy Blog offers some insight in what both Obama and McCain are paying lip service to in terms of their technology agenda. If you are of a mind that what candidates say during a campaign might bear any resemblance to what they do in office, you can read Melissa’s post […]
SC13 will have over 360 exhibits this year. In such a vibrant and growing technology space, how does your company stand out with marketing programs that deliver results? To get a perspective on this, we caught up with a seasoned HPC marketing veteran, Mike Bernhardt. Many of you know Mike’s name as the Publisher of The […]
HPCAC Spain Conference 2013 Video Gallery HPC Advisory Council Spain Conference 2013 Opening Session The Spanish Supercomputing Network HPCAC Chairman Describes the Spain Conference Boston Viridis ARM Server: Addressing the Power Challenges of Exascale High-Performance Interconnection Networks on the Road to Exascale: Challenges and Solutions Start Your Engines for the ISC’14 Student Cluster Competition BSC […]
Over at Moor Insights & Strategy Paul Teich has posted an in-depth series of features looking at Amdahl’s Law, documenting a “middle-out” model for measuring the impact of parallel computing choices. Gene Amdahl’s eponymous equation is a general, theoretical, top-down definition of the relative performance speedup that might be obtained by increasing the parallelism […]